Principal Engineer, AI Retrieval & Knowledge Platforms

What you'll do

• Design and build high-scale retrieval systems combining keyword, semantic, and vector-based search.
• Develop RAG infrastructure including indexing, ranking, and context assembly for AI applications.
• Build streaming and batch data pipelines to ingest and transform structured and unstructured data.
• Create low-latency, highly available APIs and SDKs to expose knowledge services to internal teams.
• Integrate LLMs with retrieval systems to provide grounded, context-aware experiences for agents and copilots.
• Optimize system performance through caching, sharding, and distributed query execution strategies.
• Establish observability pipelines including metrics, logs, and tracing to monitor system health.
• Lead the architecture of AI platform components while mentoring engineers on distributed systems and retrieval practices.

What we're looking for

• Minimum of 8 years of experience in backend or platform engineering.
• Experience building distributed systems, search platforms, or large-scale data services.
• Hands-on experience with APIs, microservices, and cloud-native architectures.
• Experience with search systems, indexing, or retrieval pipelines.
• Proficiency in programming with Java, Python, or Go.
• Experience with Elasticsearch/OpenSearch, vector databases, or hybrid retrieval architectures.
• Familiarity with RAG systems, embeddings, and LLM integration patterns.
• Experience with real-time data systems such as Kafka or streaming pipelines.